Skip to main content

Table 6 Average ranks for each system across the batches of Task 1a for the measures MiF and LCaF

From: An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition

System

Batch 1

Batch 2

Batch 3

 

MiF

LCaF

MiF

LCaF

MiF

LCaF

MTIFL

1.25

1.75

2.75

2.75

4.0

4.0

system3

2.75

2.75

1.0

1.0

2.0

2.0

system2

-

-

1.75

2.0

3.0

3.0

system1

-

-

-

-

1.0

1.0

MTI

-

-

-

-

3.25

3.0

RMAIP

2.50

1.75

5.0

4.5

5.25

5.5

RMAI

3.25

3.0

5.0

4.5

8.5

7.25

RMAIR

6.25

6.0

4.5

3.25

6.25

6.25

RMAIA

5.75

5.5

4.0

5.25

7.25

5.75

RMAIN

4.50

3.25

6.0

5.0

6.5

6.25

Wishart-S3-NP

8.75

9.0

14.25

15.0

-

-

Wishart-S1-KNN

8.75

9.25

12.25

12.5

-

-

Wishart-S5-Ensemble

9.5

8.0

9.50

10.25

-

-

mc4

14.75

14.25

21.0

21.0

21.5

21.25

mc3

11.0

11.25

19.75

19.75

22.0

21.5

mc5

11.25

10.0

15.0

14.75

17.0

17.0

cole_hce2

9.25

9.5

11.25

9.25

12.75

12.0

bioasq_baseline

14.0

14.0

17.75

16.75

20.75

 

cole_hce1

13.5

13.5

14.75

14.0

16.0

14.75

mc1

8.75

8.25

13.75

13.25

13.0

13.5

mc2

11.25

11.5

17.75

18.25

14.25

15.75

utai_rebayct

15.5

16.0

16.75

17.5

19.25

21.5

Wishart-S2-IR

9.75

10.75

8.5

9.25

-

-

Wishart-S5-Ngram

-

-

10.5

9.75

-

-

utai_rebayct_2

-

-

-

-

18.25

18.5

TCAM-S1

-

-

-

-

11.25

12.25

TCAM-S2

-

-

-

-

12.25

12.25

TCAM-S3

-

-

-

-

12.5

12.5

TCAM-S4

-

-

-

-

12.0

12.75

TCAM-S5

-

-

-

-

12.75

12.0

FU_System

-

-

-

-

24.0

23.25

  1. A hyphenation symbol (-) is used whenever the system participated in less than 4 times in the batch. The 4 best runs in each batch for each system were considered for its ranking.